Commit Graph

1636 Commits

Author SHA1 Message Date
James Betker
58019a2ce3 audio diffusion fid updates 2022-03-03 21:53:32 -07:00
James Betker
998c53ad4f w2v_matcher mods 2022-03-03 21:52:51 -07:00
James Betker
9029e4f20c Add a base-wrapper 2022-03-03 21:52:28 -07:00
James Betker
6873ad6660 Support functionality 2022-03-03 21:52:16 -07:00
James Betker
6af5d129ce Add experimental gradient boosting into tts7 2022-03-03 21:51:40 -07:00
James Betker
7ea84f1ac3 asdf 2022-03-03 13:43:44 -07:00
James Betker
3cd6c7f428 Get rid of unused codes in vq 2022-03-03 13:41:38 -07:00
James Betker
619da9ea28 Get rid of discretization loss 2022-03-03 13:36:25 -07:00
James Betker
beb7c8a39d asdf 2022-03-01 21:41:31 -07:00
James Betker
70fa780edb Add mechanism to export grad norms 2022-03-01 20:19:52 -07:00
James Betker
d9f8f92840 Codified fp16 2022-03-01 15:46:04 -07:00
James Betker
45ab444c04 Rework minicoder to always checkpoint 2022-03-01 14:09:18 -07:00
James Betker
db0c3340ac Implement guidance-free diffusion in eval
And a few other fixes
2022-03-01 11:49:36 -07:00
James Betker
2134f06516 Implement conditioning-free diffusion at the eval level 2022-02-27 15:11:42 -07:00
James Betker
436fe24822 Add conditioning-free guidance 2022-02-27 15:00:06 -07:00
James Betker
ac920798bb misc 2022-02-27 14:49:11 -07:00
James Betker
ba155e4e2f script for uploading models to the HF hub 2022-02-27 14:48:38 -07:00
James Betker
dbc74e96b2 w2v_matcher 2022-02-27 14:48:23 -07:00
James Betker
42879d7296 w2v_wrapper ramping dropout mode
this is an experimental feature that needs some testing
2022-02-27 14:47:51 -07:00
James Betker
c375287db9 Re-instate autocasting 2022-02-25 11:06:18 -07:00
James Betker
34ee32a90e get rid of autocasting in tts7 2022-02-24 21:53:51 -07:00
James Betker
f458f5d8f1 abort early if losses reach nan too much, and save the model 2022-02-24 20:55:30 -07:00
James Betker
18dc62453f Don't step if NaN losses are encountered. 2022-02-24 17:45:08 -07:00
James Betker
ea500ad42a Use clustered masking in udtts7 2022-02-24 07:57:26 -07:00
James Betker
7c17c8e674 gurgl 2022-02-23 21:28:24 -07:00
James Betker
e6824e398f Load dvae to cpu 2022-02-23 21:21:45 -07:00
James Betker
81017d9696 put frechet_distance on cuda 2022-02-23 21:21:13 -07:00
James Betker
9a7bbf33df f 2022-02-23 18:03:38 -07:00
James Betker
68726eac74 . 2022-02-23 17:58:07 -07:00
James Betker
b7319ab518 Support vocoder type diffusion in audio_diffusion_fid 2022-02-23 17:25:16 -07:00
James Betker
58f6c9805b adf 2022-02-22 23:12:58 -07:00
James Betker
03752c1cd6 Report NaN 2022-02-22 23:09:37 -07:00
James Betker
7201b4500c default text_to_sequence cleaners 2022-02-21 19:14:22 -07:00
James Betker
ba7f54c162 w2v: new inference function 2022-02-21 19:13:03 -07:00
James Betker
896ac029ae allow continuation of samples encountered 2022-02-21 19:12:50 -07:00
James Betker
6313a94f96 eval: integrate a n-gram language model into decoding 2022-02-21 19:12:34 -07:00
James Betker
af50afe222 pairedvoice: error out if clip is too short 2022-02-21 19:11:10 -07:00
James Betker
38802a96c8 remove timesteps from cond calculation 2022-02-21 12:32:21 -07:00
James Betker
668876799d unet_diffusion_tts7 2022-02-20 15:22:38 -07:00
James Betker
0872e17e60 unified_voice mods 2022-02-19 20:37:35 -07:00
James Betker
7b12799370 Reformat mel_text_clip for use in eval 2022-02-19 20:37:26 -07:00
James Betker
bcba65c539 DataParallel Fix 2022-02-19 20:36:35 -07:00
James Betker
34001ad765 et 2022-02-18 18:52:33 -07:00
James Betker
baf7b65566 Attempt to make w2v play with DDP AND checkpointing 2022-02-18 18:47:11 -07:00
James Betker
f3776f1992 reset ctc loss from "mean" to "sum" 2022-02-17 22:00:58 -07:00
James Betker
2b20da679c make spec_augment a parameter 2022-02-17 20:22:05 -07:00
James Betker
a813fbed9c Update to evaluator 2022-02-17 17:30:33 -07:00
James Betker
e1d71e1bd5 w2v_wrapper: get rid of ctc attention mask 2022-02-15 20:54:40 -07:00
James Betker
79e8f36d30 Convert CLIP models into new folder 2022-02-15 20:53:07 -07:00
James Betker
8f767b8b4f ... 2022-02-15 07:08:17 -07:00
James Betker
29e07913a8 Fix 2022-02-15 06:58:11 -07:00
James Betker
dd585df772 LAMB optimizer 2022-02-15 06:48:13 -07:00
James Betker
2bdb515068 A few mods to make wav2vec2 trainable with DDP on DLAS 2022-02-15 06:28:54 -07:00
James Betker
52b61b9f77 Update scripts and attempt to figure out how UnifiedVoice could be used to produce CTC codes 2022-02-13 20:48:06 -07:00
James Betker
a4f1641eea Add & refine WER evaluator for w2v 2022-02-13 20:47:29 -07:00
James Betker
e16af944c0 BSO fix 2022-02-12 20:01:04 -07:00
James Betker
29534180b2 w2v fine tuner 2022-02-12 20:00:59 -07:00
James Betker
0c3cc5ebad use script updates to fix output size disparities 2022-02-12 20:00:46 -07:00
James Betker
15fd60aad3 Allow EMA training to be disabled 2022-02-12 20:00:23 -07:00
James Betker
3252972057 ctc_code_gen mods 2022-02-12 19:59:54 -07:00
James Betker
35170c77b3 fix sweep 2022-02-11 11:43:11 -07:00
James Betker
c6b6d120fe fix ranking 2022-02-11 11:34:57 -07:00
James Betker
095944569c deep_update dicts 2022-02-11 11:32:25 -07:00
James Betker
ab1f6e8ac6 deepcopy map 2022-02-11 11:29:32 -07:00
James Betker
496fb81997 use fork instead 2022-02-11 11:22:25 -07:00
James Betker
4abc094b47 fix train bug 2022-02-11 11:18:15 -07:00
James Betker
006add64c5 sweep fix 2022-02-11 11:17:08 -07:00
James Betker
102142d1eb f 2022-02-11 11:05:13 -07:00
James Betker
40b08a52d0 dafuk 2022-02-11 11:01:31 -07:00
James Betker
f6a7f12cad Remove broken evaluator 2022-02-11 11:00:29 -07:00
James Betker
46b97049dc Fix eval 2022-02-11 10:59:32 -07:00
James Betker
5175b7d91a training sweeper checkin 2022-02-11 10:46:37 -07:00
James Betker
302ac8652d Undo mask during training 2022-02-11 09:35:12 -07:00
James Betker
618a20412a new rev of ctc_code_gen with surrogate LM loss 2022-02-10 23:09:57 -07:00
James Betker
d1d1ae32a1 audio diffusion frechet distance measurement! 2022-02-10 22:55:46 -07:00
James Betker
23a310b488 Fix BSO 2022-02-10 20:54:51 -07:00
James Betker
1e28e02f98 BSO improvement to make it work with distributed optimizers 2022-02-10 09:53:13 -07:00
James Betker
836eb08afb Update BSO to use the proper step size 2022-02-10 09:44:15 -07:00
James Betker
820a29f81e ctc code gen mods 2022-02-10 09:44:01 -07:00
James Betker
ac9417b956 ctc_code_gen: mask out all padding tokens 2022-02-09 17:26:30 -07:00
James Betker
a930f2576e Begin a migration to specifying training rate on megasamples instead of arbitrary "steps"
This should help me greatly in tuning models.  It's also necessary now that batch size isn't really
respected; we simply step once the gradient direction becomes unstable.
2022-02-09 17:25:05 -07:00
James Betker
93ca619267 script updates 2022-02-09 14:26:52 -07:00
James Betker
ddb77ef502 ctc_code_gen: use a mean() on the ConditioningEncoder 2022-02-09 14:26:44 -07:00
James Betker
3d946356f8 batch_size_optimizer works. sweet! no more tuning batch sizes. 2022-02-09 14:26:23 -07:00
James Betker
18938248e4 Add batch_size_optimizer support 2022-02-08 23:51:31 -07:00
James Betker
9e9ae328f2 mild updates 2022-02-08 23:51:17 -07:00
James Betker
ff35d13b99 Use non-uniform noise in diffusion_tts6 2022-02-08 07:27:41 -07:00
James Betker
f44b064c5e Update scripts 2022-02-07 19:43:18 -07:00
James Betker
34fbb78671 Straight CtcCodeGenerator as an encoder 2022-02-07 15:46:46 -07:00
James Betker
c24682c668 Record load times in fast_paired_dataset 2022-02-07 15:45:38 -07:00
James Betker
65a546c4d7 Fix for tts6 2022-02-05 16:00:14 -07:00
James Betker
5ae816bead ctc gen checkin 2022-02-05 15:59:53 -07:00
James Betker
bb3d1ab03d More cleanup 2022-02-04 11:06:17 -07:00
James Betker
5cc342de66 Clean up 2022-02-04 11:00:42 -07:00
James Betker
8fb147e8ab add an autoregressive ctc code generator 2022-02-04 11:00:15 -07:00
James Betker
7f4fc55344 Update SR model 2022-02-03 21:42:53 -07:00
James Betker
de1a1d501a Move audio injectors into their own file 2022-02-03 21:42:37 -07:00
James Betker
687393de59 Add a better split_on_silence (processing_pipeline)
Going to extend this a bit more going forwards to support the entire pipeline.
2022-02-03 20:00:26 -07:00
James Betker
1d29999648 Uupdates to the TTS production scripts 2022-02-03 20:00:01 -07:00
James Betker
bc506d4bcd Mods to unet_diffusion_tts6 to support super resolution mode 2022-02-03 19:59:39 -07:00
James Betker
4249681c4b Mods to support a autoregressive CTC code generator 2022-02-03 19:58:54 -07:00
James Betker
8132766d38 tts6 2022-01-31 20:15:06 -07:00
James Betker
fbea6e8eac Adjustments to diffusion networks 2022-01-30 16:14:06 -07:00
James Betker
e58dab14c3 new diffusion updates from testing 2022-01-29 11:01:01 -07:00
James Betker
935a4e853e get rid of nil tokens in <2> 2022-01-27 22:45:57 -07:00
James Betker
0152174c0e Add wandb_step_factor argument 2022-01-27 19:58:58 -07:00
James Betker
e0e36ed98c Update use_diffuse_tts 2022-01-27 19:57:28 -07:00
James Betker
a77d376ad2 rename unet diffusion tts and add 3 2022-01-27 19:56:24 -07:00
James Betker
7badbf1b4d update usage scripts 2022-01-25 17:57:26 -07:00
James Betker
8c255811ad more fixes 2022-01-25 17:57:16 -07:00
James Betker
0f3ca28e39 Allow diffusion model to be trained with masking tokens 2022-01-25 14:26:21 -07:00
James Betker
798ed7730a i like wasting time 2022-01-24 18:12:08 -07:00
James Betker
fc09cff4b3 angry 2022-01-24 18:09:29 -07:00
James Betker
cc0d9f7216 Fix 2022-01-24 18:05:45 -07:00
James Betker
3a9e3a9db3 consolidate state 2022-01-24 17:59:31 -07:00
James Betker
dfef34ba39 Load ema to cpu memory if specified 2022-01-24 15:08:29 -07:00
James Betker
49edffb6ad Revise device mapping 2022-01-24 15:08:13 -07:00
James Betker
33511243d5 load model state dicts into the correct device
it's not clear to me that this will make a huge difference, but it's a good idea anyways
2022-01-24 14:40:09 -07:00
James Betker
3e16c509f6 Misc fixes 2022-01-24 14:31:43 -07:00
James Betker
e2ed0adbd8 use_diffuse_tts updates 2022-01-24 14:31:28 -07:00
James Betker
e420df479f Allow steps to specify which state keys to carry forward (reducing memory utilization) 2022-01-24 11:01:27 -07:00
James Betker
62475005e4 Sort data items in descending order, which I suspect will improve performance because we will hit GC less 2022-01-23 19:05:32 -07:00
James Betker
d18aec793a Revert "(re) attempt diffusion checkpointing logic"
This reverts commit b22eec8fe3.
2022-01-22 09:14:50 -07:00
James Betker
b22eec8fe3 (re) attempt diffusion checkpointing logic 2022-01-22 08:34:40 -07:00
James Betker
8f48848f91 misc 2022-01-22 08:23:29 -07:00
James Betker
851070075a text<->cond clip
I need that universal clip..
2022-01-22 08:23:14 -07:00
James Betker
8ada52ccdc Update LR layers to checkpoint better 2022-01-22 08:22:57 -07:00
James Betker
ce929a6b3f Allow grad scaler to be enabled even in fp32 mode 2022-01-21 23:13:24 -07:00
James Betker
91b4b240ac dont pickle unique files 2022-01-21 00:02:06 -07:00
James Betker
7fef7fb9ff Update fast_paired_dataset to report how many audio files it is actually using 2022-01-20 21:49:38 -07:00
James Betker
ed35cfe393 Update inference scripts 2022-01-20 11:28:50 -07:00
James Betker
20312211e0 Fix bug in code alignment 2022-01-20 11:28:12 -07:00
James Betker
8e2439f50d Decrease resolution requirements to 2048 2022-01-20 11:27:49 -07:00
James Betker
4af8525dc3 Adjust diffusion vocoder to allow training individual levels 2022-01-19 13:37:59 -07:00
James Betker
ac13bfefe8 use_diffuse_tts 2022-01-19 00:35:24 -07:00
James Betker
bcd8cc51e1 Enable collated data for diffusion purposes 2022-01-19 00:35:08 -07:00
James Betker
dc9cd8c206 Update use_gpt_tts to be usable with unified_voice2 2022-01-18 21:14:17 -07:00
James Betker
7b4544b83a Add an experimental unet_diffusion_tts to perform experiments on 2022-01-18 08:38:24 -07:00
James Betker
b6190e96b2 fast_paired 2022-01-17 15:46:02 -07:00
James Betker
1d30d79e34 De-specify fast-paired-dataset 2022-01-16 21:20:00 -07:00
James Betker
2b36ca5f8e Revert paired back 2022-01-16 21:10:46 -07:00
James Betker
ad3e7df086 Split the fast random into its own new dataset 2022-01-16 21:10:11 -07:00
James Betker
7331862755 Updated paired to randomly index data, offsetting memory costs and speeding up initialization 2022-01-16 21:09:22 -07:00
James Betker
37e4e737b5 a few fixes 2022-01-16 15:17:17 -07:00
James Betker
35db5ebf41 paired_voice_audio_dataset - aligned codes support 2022-01-15 17:38:26 -07:00
James Betker
3f177cd2b3 requirements 2022-01-15 17:28:59 -07:00
James Betker
b398ecca01 wer fix 2022-01-15 17:28:17 -07:00
James Betker
9100e7fa9b Add a diffusion network that takes aligned text instead of MELs 2022-01-15 17:28:02 -07:00
James Betker
87c83e4957 update wer script 2022-01-13 17:08:49 -07:00
James Betker
009a1e8404 Add a new diffusion_vocoder that should be trainable faster
This new one has a "cheating" top layer, that does not feed down into the unet encoder,
but does consume the outputs of the unet. This cheater only operates on half of the input,
while the rest of the unet operates on the full input. This limits the dimensionality of this last
layer, on the assumption that these last layers consume by far the most computation and memory,
but do not require the full input context.

Losses are only computed on half of the aggregate input.
2022-01-11 17:26:07 -07:00